From mboxrd@z Thu Jan 1 00:00:00 1970 From: Neil Horman Subject: Re: [PATCH v2 0/2] dpdk: Allow for dynamic enablement of some isolated features Date: Wed, 30 Jul 2014 15:34:04 -0400 Message-ID: <20140730193404.GC3296@hmsreliant.think-freely.org> References: <1406665466-29654-1-git-send-email-nhorman@tuxdriver.com> <1406731769-18523-1-git-send-email-nhorman@tuxdriver.com> <53D9418A.5020308@intel.com> Mime-Version: 1.0 Content-Type: text/plain; charset=us-ascii Cc: dev-VfR2kkLFssw@public.gmane.org To: Venky Venkatesan Return-path: Content-Disposition: inline In-Reply-To: <53D9418A.5020308-ral2JQCrhuEAvxtiuMwx3w@public.gmane.org> List-Id: patches and discussions about DPDK List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Errors-To: dev-bounces-VfR2kkLFssw@public.gmane.org Sender: "dev" On Wed, Jul 30, 2014 at 12:03:38PM -0700, Venky Venkatesan wrote: > Neil, > > >Hey all- > > I've been trying to update the fedora dpdk package to support VFIO > >enabled drivers and ran into a problem in which ixgbe didn't compile because the > >rxtx_vec code uses sse4.2 instruction intrinsics, which aren't supported in the > >default config I have. I tried to remedy this by replacing the intrinsics with > >the __builtin macros, but it was pointed out (correctly), that this doesn't work > >properly. So this is my second attempt, which I actually like a bit better. I > >noted that code that uses intrinsics (ixgbe and the acl library), don't need to > >have those instructions turned on build-wide. Rather, we can just enable the > >instructions in the specific code we want to build with support for that, and > >test for instruction support dynamically at run time. This allows me to build > >the dpdk for a generic platform, but in such a way that some optimizations can > >be used if the executing cpu supports them at run time. > > > >Change notes: > > > >v2) > > * Added Log messages to run time check failures per Konstantin > > * Removed run time check caching in acl per Konstantin > > > >Signed-off-by: Neil Horman > >CC: Thomas Monjalon > > > > One possible change to look at - the _mm_shuffle_epi8 is something that is > available all the way from SSSE3, so you should be able to leave that in. > The SSE4.2 dependency is only for the popcount (and __builtin_popcountll > will work for that anyway). That should make things simpler. > > -Venky > ugh, actually both the ixgbe and acl libraries use the popcnt instruction, so I think I'd rather just keep the sse4.2 instruction set as it is, unless you think the __builtin_popcnt is equally performant. Neil